{"id":20346938,"url":"https://github.com/dacossti/llm-task-planner","last_synced_at":"2026-07-20T17:32:37.370Z","repository":{"id":244209454,"uuid":"814548128","full_name":"Dacossti/LLM-Task-Planner","owner":"Dacossti","description":"An intelligent robotic task planner built on ROS 2 Humble, leveraging Large Language Models for high-level reasoning and Nav2 for autonomous navigation","archived":false,"fork":false,"pushed_at":"2026-02-15T22:52:17.000Z","size":189711,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-02-16T06:15:20.412Z","etag":null,"topics":["automated-planning","behavior-tree","few-shot-learning","gazebo","gazebo-simulator","gemini-api","huggingface","large-language-models","natural-language-processing","nav2-plugins","openai","openrouter-api","python","robotics","ros2-humble","rviz","theta-star","ubuntu","wsl","wsl-ubuntu"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Dacossti.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-06-13T08:16:59.000Z","updated_at":"2026-02-15T22:52:20.000Z","dependencies_parsed_at":"2024-06-13T12:43:07.989Z","dependency_job_id":"0bca6ca8-7300-43ed-a284-da088cb5a3b4","html_url":"https://github.com/Dacossti/LLM-Task-Planner","commit_stats":null,"previous_names":["dacossti/llm-task-planner"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Dacossti/LLM-Task-Planner","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dacossti%2FLLM-Task-Planner","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dacossti%2FLLM-Task-Planner/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dacossti%2FLLM-Task-Planner/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dacossti%2FLLM-Task-Planner/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Dacossti","download_url":"https://codeload.github.com/Dacossti/LLM-Task-Planner/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dacossti%2FLLM-Task-Planner/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35695245,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"ssl_error","status_checked_at":"2026-07-20T02:08:09.736Z","response_time":111,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["automated-planning","behavior-tree","few-shot-learning","gazebo","gazebo-simulator","gemini-api","huggingface","large-language-models","natural-language-processing","nav2-plugins","openai","openrouter-api","python","robotics","ros2-humble","rviz","theta-star","ubuntu","wsl","wsl-ubuntu"],"created_at":"2024-11-14T22:14:44.191Z","updated_at":"2026-07-20T17:32:37.345Z","avatar_url":"https://github.com/Dacossti.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM-Task-Planner\n\nВ настоящее время больщие языковые модели, такие как GPT, используются все чаще и чаще: будь то в бизнесе, развлечениях и, конечно же, в образовании.\n\nВ этой работе мы предлагаем использовать GPT-3 в качестве планировщика, чтобы позволить воплощенным агентам, то есть роботам, понимать естественный язык и быстро научиться выполнять новые задачи на основе плана, сгенерированного GPT-3.\n\nНапример, если бы вы собирались приготовить себе омлет, вам, несомненно, потребовались бы яйца, сковорода, немного масла и немного соли.\n\nПоскольку здравый смысл подсказывает, что яйца часто хранятся в холодильнике, вы бы подошли к холодильнику, взяли яйца, затем вы бы пошли на кухню, взяли сковороду, включили духовку, поставили сковороду на духовку, налили масло в сковороду, разбейте на мелкие кусочки. яйца, положить немного соли, подождать 1-2 минуты, выключить духовку и вынуть сковороду из духовки.\n\nПо сути, наш алгоритм позволяет агенту (роботу) делать то же самое. В данном конкретном случае он создал бы план, который выглядит примерно так:\n\n- Navigate fridge\n- OpenObject fridge\n- PickupObject eggs\n- CloseObject fridge\n- Navigate kitchen\n- PickupObject pan\n- PickupObject oil\n- ToggleObjectOn oven\n- PutObject pan oven\n- PutObject oil pan\n- PutObject eggs pan\n- PutObject salt pan\n- ToggleObjectOff oven\n\n# Quickstart\n\n- Установить нужные библиотеки\n\n```\npip install -r requirements.txt\n```\n\n- Запустить main.py\n```\npython main.py\n```\n\n\u003e **Note**\n\u003e Не забудьте указать свой секретный ключ openai в файле main.py\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdacossti%2Fllm-task-planner","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdacossti%2Fllm-task-planner","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdacossti%2Fllm-task-planner/lists"}